1 Hexagon is Qualcomm's very long instruction word (VLIW) digital signal
2 processor(DSP). We also support Hexagon Vector eXtensions (HVX). HVX
3 is a wide vector coprocessor designed for high performance computer vision,
4 image processing, machine learning, and other workloads.
6 The following versions of the Hexagon core are supported
8 https://developer.qualcomm.com/downloads/qualcomm-hexagon-v67-programmer-s-reference-manual
10 https://developer.qualcomm.com/downloads/qualcomm-hexagon-v66-hvx-programmer-s-reference-manual
12 We presented an overview of the project at the 2019 KVM Forum.
13 https://kvmforum2019.sched.com/event/Tmwc/qemu-hexagon-automatic-translation-of-the-isa-manual-pseudcode-to-tiny-code-instructions-of-a-vliw-architecture-niccolo-izzo-revng-taylor-simpson-qualcomm-innovation-center
15 *** Tour of the code ***
17 The qemu-hexagon implementation is a combination of qemu and the Hexagon
18 architecture library (aka archlib). The three primary directories with
19 Hexagon-specific code are
22 This has all the instruction and packet semantics
23 qemu/target/hexagon/imported
24 These files are imported with very little modification from archlib
25 *.idef Instruction semantics definition
26 macros.def Mapping of macros to instruction attributes
27 encode*.def Encoding patterns for each instruction
28 iclass.def Instruction class definitions used to determine
29 legal VLIW slots for each instruction
30 qemu/target/hexagon/idef-parser
31 Parser that, given the high-level definitions of an instruction,
32 produces a C function generating equivalent tiny code instructions.
34 qemu/linux-user/hexagon
35 Helpers for loading the ELF file and making Linux system calls,
38 We start with scripts that generate a bunch of include files. This
39 is a two step process. The first step is to use the C preprocessor to expand
40 macros inside the architecture definition files. This is done in
41 target/hexagon/gen_semantics.c. This step produces
42 <BUILD_DIR>/target/hexagon/semantics_generated.pyinc.
43 That file is consumed by the following python scripts to produce the indicated
44 header files in <BUILD_DIR>/target/hexagon
45 gen_opcodes_def.py -> opcodes_def_generated.h.inc
46 gen_op_regs.py -> op_regs_generated.h.inc
47 gen_printinsn.py -> printinsn_generated.h.inc
48 gen_op_attribs.py -> op_attribs_generated.h.inc
49 gen_helper_protos.py -> helper_protos_generated.h.inc
50 gen_shortcode.py -> shortcode_generated.h.inc
51 gen_tcg_funcs.py -> tcg_funcs_generated.c.inc
52 gen_tcg_func_table.py -> tcg_func_table_generated.c.inc
53 gen_helper_funcs.py -> helper_funcs_generated.c.inc
54 gen_idef_parser_funcs.py -> idef_parser_input.h
56 Qemu helper functions have 3 parts
57 DEF_HELPER declaration indicates the signature of the helper
58 gen_helper_<NAME> will generate a TCG call to the helper function
59 The helper implementation
61 Here's an example of the A2_add instruction.
62 Instruction tag A2_add
63 Assembly syntax "Rd32=add(Rs32,Rt32)"
64 Instruction semantics "{ RdV=RsV+RtV;}"
66 By convention, the operands are identified by letter
67 RdV is the destination register
68 RsV, RtV are source registers
70 The generator uses the operand naming conventions (see large comment in
71 hex_common.py) to determine the signature of the helper function. Here are the
74 helper_protos_generated.h.inc
75 DEF_HELPER_3(A2_add, s32, env, s32, s32)
77 tcg_funcs_generated.c.inc
78 static void generate_A2_add(
84 TCGv RdV = tcg_temp_local_new();
85 const int RdN = insn->regno[0];
86 TCGv RsV = hex_gpr[insn->regno[1]];
87 TCGv RtV = hex_gpr[insn->regno[2]];
88 gen_helper_A2_add(RdV, cpu_env, RsV, RtV);
89 gen_log_reg_write(RdN, RdV);
90 ctx_log_reg_write(ctx, RdN);
94 helper_funcs_generated.c.inc
95 int32_t HELPER(A2_add)(CPUHexagonState *env, int32_t RsV, int32_t RtV)
97 uint32_t slot __attribute__((unused)) = 4;
103 Note that generate_A2_add updates the disassembly context to be processed
104 when the packet commits (see "Packet Semantics" below).
106 The generator checks for fGEN_TCG_<tag> macro. This allows us to generate
107 TCG code instead of a call to the helper. If defined, the macro takes 1
109 C semantics (aka short code)
111 This allows the code generator to override the auto-generated code. In some
112 cases this is necessary for correct execution. We can also override for
113 faster emulation. For example, calling a helper for add is more expensive
114 than generating a TCG add operation.
116 The gen_tcg.h file has any overrides. For example, we could write
117 #define fGEN_TCG_A2_add(GENHLPR, SHORTCODE) \
118 tcg_gen_add_tl(RdV, RsV, RtV)
120 The instruction semantics C code relies heavily on macros. In cases where the
121 C semantics are specified only with macros, we can override the default with
122 the short semantics option and #define the macros to generate TCG code. One
123 example is L2_loadw_locked:
124 Instruction tag L2_loadw_locked
125 Assembly syntax "Rd32=memw_locked(Rs32)"
126 Instruction semantics "{ fEA_REG(RsV); fLOAD_LOCKED(1,4,u,EA,RdV) }"
128 In gen_tcg.h, we use the shortcode
129 #define fGEN_TCG_L2_loadw_locked(SHORTCODE) \
132 There are also cases where we brute force the TCG code generation.
133 Instructions with multiple definitions are examples. These require special
134 handling because qemu helpers can only return a single value.
136 For HVX vectors, the generator behaves slightly differently. The wide vectors
137 won't fit in a TCGv or TCGv_i64, so we pass TCGv_ptr variables to pass the
138 address to helper functions. Here's an example for an HVX vector-add-word
140 static void generate_V6_vaddw(
141 CPUHexagonState *env,
146 const int VdN = insn->regno[0];
147 const intptr_t VdV_off =
148 ctx_future_vreg_off(ctx, VdN, 1, true);
149 TCGv_ptr VdV = tcg_temp_local_new_ptr();
150 tcg_gen_addi_ptr(VdV, cpu_env, VdV_off);
151 const int VuN = insn->regno[1];
152 const intptr_t VuV_off =
153 vreg_src_off(ctx, VuN);
154 TCGv_ptr VuV = tcg_temp_local_new_ptr();
155 const int VvN = insn->regno[2];
156 const intptr_t VvV_off =
157 vreg_src_off(ctx, VvN);
158 TCGv_ptr VvV = tcg_temp_local_new_ptr();
159 tcg_gen_addi_ptr(VuV, cpu_env, VuV_off);
160 tcg_gen_addi_ptr(VvV, cpu_env, VvV_off);
161 TCGv slot = tcg_constant_tl(insn->slot);
162 gen_helper_V6_vaddw(cpu_env, VdV, VuV, VvV, slot);
164 gen_log_vreg_write(ctx, VdV_off, VdN, EXT_DFL, insn->slot, false);
165 ctx_log_vreg_write(ctx, VdN, EXT_DFL, false);
166 tcg_temp_free_ptr(VdV);
167 tcg_temp_free_ptr(VuV);
168 tcg_temp_free_ptr(VvV);
171 Notice that we also generate a variable named <operand>_off for each operand of
172 the instruction. This makes it easy to override the instruction semantics with
173 functions from tcg-op-gvec.h. Here's the override for this instruction.
174 #define fGEN_TCG_V6_vaddw(SHORTCODE) \
175 tcg_gen_gvec_add(MO_32, VdV_off, VuV_off, VvV_off, \
176 sizeof(MMVector), sizeof(MMVector))
178 Finally, we notice that the override doesn't use the TCGv_ptr variables, so
179 we don't generate them when an override is present. Here is what we generate
180 when the override is present.
181 static void generate_V6_vaddw(
182 CPUHexagonState *env,
187 const int VdN = insn->regno[0];
188 const intptr_t VdV_off =
189 ctx_future_vreg_off(ctx, VdN, 1, true);
190 const int VuN = insn->regno[1];
191 const intptr_t VuV_off =
192 vreg_src_off(ctx, VuN);
193 const int VvN = insn->regno[2];
194 const intptr_t VvV_off =
195 vreg_src_off(ctx, VvN);
196 fGEN_TCG_V6_vaddw({ fHIDE(int i;) fVFOREACH(32, i) { VdV.w[i] = VuV.w[i] + VvV.w[i] ; } });
197 gen_log_vreg_write(ctx, VdV_off, VdN, EXT_DFL, insn->slot, false);
198 ctx_log_vreg_write(ctx, VdN, EXT_DFL, false);
201 In addition to instruction semantics, we use a generator to create the decode
202 tree. This generation is also a two step process. The first step is to run
203 target/hexagon/gen_dectree_import.c to produce
204 <BUILD_DIR>/target/hexagon/iset.py
205 This file is imported by target/hexagon/dectree.py to produce
206 <BUILD_DIR>/target/hexagon/dectree_generated.h.inc
212 This file contains the definition of the CPUHexagonState struct. It is the
213 runtime information for each thread and contains stuff like the GPR and
219 The Hexagon arch lib relies heavily on macros for the instruction semantics.
220 This is a great advantage for qemu because we can override them for different
221 purposes. You will also notice there are sometimes two definitions of a macro.
222 The QEMU_GENERATE variable determines whether we want the macro to generate TCG
223 code. If QEMU_GENERATE is not defined, we want the macro to generate vanilla
224 C code that will work in the helper implementation.
228 The functions in this file generate TCG code for a translation block. Some
229 important functions in this file are
231 gen_start_packet - initialize the data structures for packet semantics
232 gen_commit_packet - commit the register writes, stores, etc for a packet
233 decode_and_translate_packet - disassemble a packet and generate code
238 These files create a function for each instruction. It is mostly composed of
239 fGEN_TCG_<tag> definitions followed by including tcg_funcs_generated.c.inc.
243 This file contains the implementations of all the helpers. There are a few
244 general purpose helpers, but most of them are generated by including
245 helper_funcs_generated.c.inc. There are also several helpers used for debugging.
248 *** Packet Semantics ***
250 VLIW packet semantics differ from serial semantics in that all input operands
251 are read, then the operations are performed, then all the results are written.
252 For exmaple, this packet performs a swap of registers r0 and r1
254 Note that the result is different if the instructions are executed serially.
256 Packet semantics dictate that we defer any changes of state until the entire
257 packet is committed. We record the results of each instruction in a side data
258 structure, and update the visible processor state when we commit the packet.
260 The data structures are divided between the runtime state and the translation
263 During the TCG generation (see translate.[ch]), we use the DisasContext to
264 track what needs to be done during packet commit. Here are the relevant
267 reg_log list of registers written
268 reg_log_idx index into ctx_reg_log
269 pred_log list of predicates written
270 pred_log_idx index into ctx_pred_log
271 store_width width of stores (indexed by slot)
273 During runtime, the following fields in CPUHexagonState (see cpu.h) are used
275 new_value new value of a given register
276 reg_written boolean indicating if register was written
277 new_pred_value new value of a predicate register
278 pred_written boolean indicating if predicate was written
279 mem_log_stores record of the stores (indexed by slot)
281 For Hexagon Vector eXtensions (HVX), the following fields are used
282 VRegs Vector registers
283 future_VRegs Registers to be stored during packet commit
284 tmp_VRegs Temporary registers *not* stored during commit
285 VRegs_updated Mask of predicated vector writes
286 QRegs Q (vector predicate) registers
287 future_QRegs Registers to be stored during packet commit
288 QRegs_updated Mask of predicated vector writes
292 You can turn on a lot of debugging by changing the HEX_DEBUG macro to 1 in
293 internal.h. This will stream a lot of information as it generates TCG and
296 To track down nasty issues with Hexagon->TCG generation, we compare the
297 execution results with actual hardware running on a Hexagon Linux target.
298 Run qemu with the "-d cpu" option. Then, we can diff the results and figure
299 out where qemu and hardware behave differently.
301 The stacks are located at different locations. We handle this by changing
302 env->stack_adjust in translate.c. First, set this to zero and run qemu.
303 Then, change env->stack_adjust to the difference between the two stack
304 locations. Then rebuild qemu and run again. That will produce a very
307 Here are some handy places to set breakpoints
309 At the call to gen_start_packet for a given PC (note that the line number
310 might change in the future)
311 br translate.c:602 if ctx->base.pc_next == 0xdeadbeef
312 The helper function for each instruction is named helper_<TAG>, so here's
313 an example that will set a breakpoint at the start
315 If you have the HEX_DEBUG macro set, the following will be useful
316 At the start of execution of a packet for a given PC
317 br helper_debug_start_packet if env->gpr[41] == 0xdeadbeef
318 At the end of execution of a packet for a given PC
319 br helper_debug_commit_end if env->this_PC == 0xdeadbeef